From b5875222de2fb91339db79a753677ba4f68120d0 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 11 Dec 2015 13:14:28 -0700 Subject: NVMe: IO ending fixes on surprise removal This patch fixes a lost request discovered during IO + hot removal. The driver's pci removal deletes gendisks prior to shutting down the controller to allow dirty data to sync. Dirty data can not be synced on a surprise removal, though, and would potentially block indefinitely. The driver previously had marked the queue as dying in this scenario to prevent new requests from attempting, however it will still block for requests that already entered the queue. This patch fixes this by quiescing IO first, then aborting the requeued requests before deleting disks. Reported-by: Sujith Pandel Signed-off-by: Keith Busch Tested-by: Sujith Pandel Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9e294ff4e652..0c67b57be83c 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2540,8 +2540,17 @@ static void nvme_ns_remove(struct nvme_ns *ns) { bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue); - if (kill) + if (kill) { blk_set_queue_dying(ns->queue); + + /* + * The controller was shutdown first if we got here through + * device removal. The shutdown may requeue outstanding + * requests. These need to be aborted immediately so + * del_gendisk doesn't block indefinitely for their completion. + */ + blk_mq_abort_requeue_list(ns->queue); + } if (ns->disk->flags & GENHD_FL_UP) del_gendisk(ns->disk); if (kill || !blk_queue_dying(ns->queue)) { @@ -2977,6 +2986,15 @@ static void nvme_dev_remove(struct nvme_dev *dev) { struct nvme_ns *ns, *next; + if (nvme_io_incapable(dev)) { + /* + * If the device is not capable of IO (surprise hot-removal, + * for example), we need to quiesce prior to deleting the + * namespaces. This will end outstanding requests and prevent + * attempts to sync dirty data. + */ + nvme_dev_shutdown(dev); + } list_for_each_entry_safe(ns, next, &dev->namespaces, list) nvme_ns_remove(ns); } -- cgit v1.2.3 From 23688bf4f830a89866fd0ed3501e342a7360fe4f Mon Sep 17 00:00:00 2001 From: Junichi Nomura Date: Tue, 22 Dec 2015 10:23:44 -0700 Subject: block: ensure to split after potentially bouncing a bio blk_queue_bio() does split then bounce, which makes the segment counting based on pages before bouncing and could go wrong. Move the split to after bouncing, like we do for blk-mq, and the we fix the issue of having the bio count for segments be wrong. Fixes: 54efd50bfd87 ("block: make generic_make_request handle arbitrarily sized bios") Cc: stable@vger.kernel.org Tested-by: Artem S. Tashkinov Signed-off-by: Jens Axboe --- block/blk-core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index 3636be469fa2..c487b94c59e3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1689,8 +1689,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) struct request *req; unsigned int request_count = 0; - blk_queue_split(q, &bio, q->bio_split); - /* * low level driver can indicate that it wants pages above a * certain limit bounced to low memory (ie for highmem, or even @@ -1698,6 +1696,8 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) */ blk_queue_bounce(q, &bio); + blk_queue_split(q, &bio, q->bio_split); + if (bio_integrity_enabled(bio) && bio_integrity_prep(bio)) { bio->bi_error = -EIO; bio_endio(bio); -- cgit v1.2.3 From e8271201462710dbbaa0448b768428606724ca90 Mon Sep 17 00:00:00 2001 From: Mike Krinkin Date: Tue, 15 Dec 2015 12:56:40 +0300 Subject: null_blk: fix use-after-free error blk_end_request_all may free request, so we need to save request_queue pointer before blk_end_request_all call. The problem was introduced in commit cf8ecc5a8455266f8d51 ("null_blk: guarantee device restart in all irq modes") and causes general protection fault with slab poisoning enabled. Fixes: cf8ecc5a8455266f8d51 ("null_blk: guarantee device restart in all irq modes") Signed-off-by: Mike Krinkin Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- drivers/block/null_blk.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 8162475d96b5..a428e4ef71fd 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -219,6 +219,9 @@ static void end_cmd(struct nullb_cmd *cmd) { struct request_queue *q = NULL; + if (cmd->rq) + q = cmd->rq->q; + switch (queue_mode) { case NULL_Q_MQ: blk_mq_end_request(cmd->rq, 0); @@ -232,9 +235,6 @@ static void end_cmd(struct nullb_cmd *cmd) goto free_cmd; } - if (cmd->rq) - q = cmd->rq->q; - /* Restart queue if needed, as we are freeing a tag */ if (q && !q->mq_ops && blk_queue_stopped(q)) { unsigned long flags; -- cgit v1.2.3